Video anomaly detection with compact feature sets for online performance
- Submitting institution
-
The University of Warwick
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 10582
- Type
- D - Journal article
- DOI
-
10.1109/TIP.2017.2695105
- Title of journal
- IEEE Transactions on Image Processing
- Article number
- -
- First page
- 3463
- Volume
- 26
- Issue
- 7
- ISSN
- 1057-7149
- Open access status
- Not compliant
- Month of publication
- July
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
2
- Research group(s)
-
A - Applied Computing
- Citation count
- 45
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Published in the top image processing journal, this paper presents a novel machine learning framework for real-time detection of abnormal events in videos. This research, which was co-funded by Consejo Nacional de Ciencia y Tecnologia (CONACyT), Mexico and the Horizon2020 RISE project IDENTITY, is being commercialised by Warwick Ventures and has resulted in the organisation of a tutorial at the 16th IEEE International Conference on Advanced Video Signal-based Surveillance (AVSS 2019). It has impacted researchers working on crowd anomaly detection (Kyung, Korea Advanced Institute of Science and Technology), and has led to funding from the Defence and Security Accelerator, UK.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -